Skip to main content

Digital Trends may earn a commission when you buy through links on our site. Why trust us?

Leak suggests mobile version of Nvidia’s GTX 1070 and 1060 won’t differ much from the desktop

Now that Nvidia’s Pascal-based GeForce GTX 1070 and GTX 1060 cards are available on the market, the spotlight falls on the mobile versions of these graphics chips. While nothing official has hit the streets, reports have surfaced showing these two mobile GPUs listed separately in the GPU-Z application. So much for that rumor about scrapping high-end mobile versions for full-blown GPUs in notebooks? Perhaps not.

For starters, a screenshot provided by BenchLife shows that the mobile version of the GTX 1070 will have 2,048 CUDA cores, which is 128 more than the desktop version. There are also 64 Render Output Units, 170 Texture Memory Units, a pixel fill rate of 92.4 gigapixels per second, and a texture fill rate of 245.3 gigatexels per second. The chip is backed by 8GB of GDDR5 memory from Samsung, a 256-bit bus width, and a memory bandwidth of 256.3GB per second.

Recommended Videos

As for other details, the mobile GTX 1070 chip has a base clock speed of 1,443MHz, a boost clock speed of 1,645MHz, and a memory clock speed of 2,002MHz. Nvidia SLI is shown as disabled, and the chip shows it to be compatible with DirectCompute 5.0.

As for the mobile version of the GTX 1060, a screenshot of the GPU-Z app provided by PurePC shows that it has 1,280 CUDA cores, the same amount offered in the desktop version. Also, there are 48 Render Output Units, 106 Texture Memory Units, a pixel fill rate of 67.4 gigapixels per second, and a texture fill rate of 148.9 gigatexels per second.

The unannounced mobile chip will supposedly have 6GB of GDDR5 memory provided by Samsung, with a 192-bit bus width and a bandwidth of 192.2GB per second. The chip’s base clock speed shows to be 1,405MHz, its boost clock speed at 1,671MHz, and its memory clock speed at 2,002MHz. Nvidia SLI is also shown to be disabled for this specific graphics chip.

Basically, the mobile GTX 1060 offers similar specs as the desktop version, but with a lower clock speed. The desktop version, launched on Tuesday, has a base clock speed of 1,506MHz and a boost clock speed of 1,709MHz. As for the mobile GTX 1070 chip, the CUDA count is higher, as previously stated, but the clock speeds are lower, as the desktop version has a base clock of 1,506MHz, and a boost clock of 1,683MHz.

As the two GPU-Z screenshots suggest, Nvidia’s Pascal architecture seemingly allows the company to cram a desktop-grade GPU into a notebook, as the previous rumor suggested. Of the two examples, the GTX 1070 is the most altered component with the added cores and reduced clock speeds, but otherwise the difference isn’t that far off…. if the GPU-Z screenshots are indeed authentic.

In addition to the GPU-Z app, PurePC shows a screenshot of a 3DMark Firestrike benchmark using the mobile GTX 1060 chip. The gaming laptop used in the test also included an Intel Core i7-6700K processor and 16GB of system memory. This laptop obtained a score of 10,295 points in the benchmark, which seems mighty impressive for a notebook with a “mobile” GPU installed.

Kevin Parrish
Kevin started taking PCs apart in the 90s when Quake was on the way and his PC lacked the required components. Since then…
Nvidia’s laptop RTX 4080 obliterates its predecessor in a leaked benchmark
Three RTX 4080 cards sitting on a pink background.

Nvidia's RTX 4080 is already out in its desktop version, but all signs point to it soon being released as a laptop GPU. Some people have already gotten their hands on laptops equipped with one of Nvidia's best graphics cards, and we now know the benchmark scores of one such laptop.

The test spells good news for Nvidia's upcoming mobile GPU -- the RTX 4080 was able to beat the RTX 3080 by a whopping 42%. Here's what we know about the upcoming RTX 4080M.

Read more
Nvidia RTX 4080 costs too much, recent survey shows
Nvidia GeForce RTX 4080 graphics card is shown flying over green perspective lines.

Nvidia's GeForce RTX 4080 is its second-most-powerful graphics card, and that high performance comes at a cost that gamers feel is too high, according to a recent survey. Priced at $1,200, it supports DirectX 12 Ultimate capability, exceeding the blazing performance of the previous generation's best, the GeForce RTX 3090 Ti.

Despite the amazing graphics performance of the GPU and its 16GB of memory, most gamers in a recent survey felt it was overpriced. This demonstrates how much we've come to assume that technology will continue to get faster without any significant increase in cost. That is partially true since manufacturing advances and ongoing miniaturization help, but there are other factors that can affect pricing, such as the after-effects of the global pandemic.

Read more
Gigabyte may have accidentally leaked Nvidia’s plans for the RTX 4080 12GB
Gigabyte's RTX 3090 Ti up close.

A new leak shows that Gigabyte is readying some new graphics cards, and both AMD and Nvidia fans have something to look forward to.

It seems that Gigabyte may have inadvertently confirmed previous rumors about Nvidia's plans in regard to the "unlaunched" RTX 4080 12GB.

Read more